Analyse appartements - Shapash
Interpretation des predictions appartements
Project_Information
Author : VotreNom
Description : Rapport Shapash pour appartements
Project_Name : Analyse lightgbm_appart
Model analysis
Model used : LGBMRegressor
Library : lightgbm.sklearn
Library version : 4.6.0
Model parameters :
| Parameter key | Parameter value |
|---|---|
| boosting_type | gbdt |
| objective | None |
| num_leaves | 95 |
| max_depth | 10 |
| learning_rate | 0.06774931487278521 |
| n_estimators | 294 |
| subsample_for_bin | 200000 |
| min_split_gain | 0.0 |
| min_child_weight | 0.001 |
| min_child_samples | 10 |
| subsample | 1.0 |
| subsample_freq | 0 |
| colsample_bytree | 1.0 |
| reg_alpha | 0.0 |
| reg_lambda | 0.0 |
| random_state | None |
| Parameter key | Parameter value |
|---|---|
| n_jobs | None |
| importance_type | split |
| _Booster | |
| _evals_result | {} |
| _best_score | defaultdict( |
| _best_iteration | 0 |
| _other_params | {} |
| _objective | regression |
| class_weight | None |
| _class_weight | None |
| _class_map | None |
| _n_features | 56 |
| _n_features_in | 56 |
| _classes | None |
| _n_classes | -1 |
| fitted_ | True |
Dataset analysis
Global analysis
| Training dataset | Prediction dataset | |
|---|---|---|
| number of features | NaN | 56 |
| number of observations | NaN | 2,759 |
| missing values | NaN | 0 |
| % missing values | NaN | 0 |
Univariate analysis
- CODE_IRIS
- Revenu_fiscal_de_r__f__rence_par_habitant
- STATUT_COM_UU_Banlieue
- STATUT_COM_UU_Campagne
- STATUT_COM_UU_Ville isolée
- STATUT_COM_UU_Ville-centre
- TYP_IRIS_y
- UU2020
- anciennete_annonce
- annee
- annee_construction
- annonce_exclusive
- ascenseur
- bain
- balcon
- categorie_annonceur
- cave
- charges_copro
- chauffage_energie
- chauffage_mode
- chauffage_systeme
- classe_annee
- dpeC
- dpeL
- eau
- etage
- exposition_autre
- exposition_est
- exposition_nord
- exposition_sud
- ges_class
- ges_class_encoded
- logement_neuf
- mapCoordonneesLatitude
- mapCoordonneesLongitude
- nb_etages
- nb_logements_copro
- nb_pieces
- nb_toilettes
- places_parking
- score__conomie_brut
- score__conomie_ratio_1000
- score_commerce_brut
- score_commerce_ratio_1000
- score_culture_loisir_brut
- score_culture_loisir_ratio_1000
- score_education_brut
- score_education_ratio_1000
- score_s_curit__brut
- score_s_curit__ratio_1000
- score_sant__brut
- score_sant__ratio_1000
- score_transport_brut
- score_transport_ratio_1000
- source_imputation
- surface
CODE_IRIS - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | 135 |
| std | 78.3 |
| min | 0 |
| 25% | 58 |
| 50% | 140 |
| 75% | 204 |
| max | 289 |
Revenu_fiscal_de_r__f__rence_par_habitant - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | -0.0126 |
| std | 0.998 |
| min | -1.2 |
| 25% | -0.625 |
| 50% | -0.341 |
| 75% | 0.458 |
| max | 3.92 |
STATUT_COM_UU_Banlieue - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 2 |
| missing values | 0 |
STATUT_COM_UU_Campagne - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 2 |
| missing values | 0 |
STATUT_COM_UU_Ville isolée - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 2 |
| missing values | 0 |
STATUT_COM_UU_Ville-centre - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 2 |
| missing values | 0 |
TYP_IRIS_y - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 2 |
| missing values | 0 |
UU2020 - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | 0.0367 |
| std | 0.994 |
| min | -2.12 |
| 25% | -0.332 |
| 50% | 0.109 |
| 75% | 1 |
| max | 1 |
anciennete_annonce - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 5 |
| missing values | 0 |
annee - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 5 |
| missing values | 0 |
annee_construction - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | -0.0232 |
| std | 1.01 |
| min | -6.43 |
| 25% | -0.53 |
| 50% | -0.079 |
| 75% | 0.755 |
| max | 1.35 |
annonce_exclusive - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 2 |
| missing values | 0 |
ascenseur - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 2 |
| missing values | 0 |
bain - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 4 |
| missing values | 0 |
balcon - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 5 |
| missing values | 0 |
categorie_annonceur - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 3 |
| missing values | 0 |
cave - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 2 |
| missing values | 0 |
charges_copro - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | -0.0406 |
| std | 0.939 |
| min | -1.97 |
| 25% | -0.123 |
| 50% | -0.123 |
| 75% | -0.123 |
| max | 8.65 |
chauffage_energie - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 4 |
| missing values | 0 |
chauffage_mode - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 2 |
| missing values | 0 |
chauffage_systeme - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 3 |
| missing values | 0 |
classe_annee - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 4 |
| missing values | 0 |
dpeC - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | 0.0292 |
| std | 1.02 |
| min | -1.79 |
| 25% | -0.672 |
| 50% | -0.157 |
| 75% | 0.625 |
| max | 8.62 |
dpeL - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 7 |
| missing values | 0 |
eau - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 4 |
| missing values | 0 |
etage - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | -0.0135 |
| std | 0.976 |
| min | -0.514 |
| 25% | -0.514 |
| 50% | -0.155 |
| 75% | 0.205 |
| max | 17.5 |
exposition_autre - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 2 |
| missing values | 0 |
exposition_est - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 2 |
| missing values | 0 |
exposition_nord - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 2 |
| missing values | 0 |
exposition_sud - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 2 |
| missing values | 0 |
ges_class - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 8 |
| missing values | 0 |
ges_class_encoded - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 8 |
| missing values | 0 |
logement_neuf - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 2 |
| missing values | 0 |
mapCoordonneesLatitude - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | 0.00369 |
| std | 0.983 |
| min | -1.75 |
| 25% | -0.499 |
| 50% | -0.301 |
| 75% | 0.681 |
| max | 2.74 |
mapCoordonneesLongitude - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | -0.00558 |
| std | 0.975 |
| min | -3.59 |
| 25% | -0.413 |
| 50% | -0.157 |
| 75% | 0.358 |
| max | 1.97 |
nb_etages - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 6 |
| missing values | 0 |
nb_logements_copro - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | 0.00533 |
| std | 0.919 |
| min | -0.612 |
| 25% | -0.263 |
| 50% | -0.233 |
| 75% | -0.188 |
| max | 14.5 |
nb_pieces - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 9 |
| missing values | 0 |
nb_toilettes - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 4 |
| missing values | 0 |
places_parking - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 2 |
| missing values | 0 |
score__conomie_brut - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | 0.0215 |
| std | 1.01 |
| min | -0.896 |
| 25% | -0.815 |
| 50% | -0.654 |
| 75% | 0.992 |
| max | 1.52 |
score__conomie_ratio_1000 - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | 0.00312 |
| std | 1.01 |
| min | -2.18 |
| 25% | -0.732 |
| 50% | 0.173 |
| 75% | 0.394 |
| max | 7.58 |
score_commerce_brut - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | 0.021 |
| std | 1.01 |
| min | -0.903 |
| 25% | -0.823 |
| 50% | -0.628 |
| 75% | 0.965 |
| max | 1.53 |
score_commerce_ratio_1000 - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | -0.000406 |
| std | 0.98 |
| min | -2.36 |
| 25% | -0.659 |
| 50% | 0.228 |
| 75% | 0.713 |
| max | 6.05 |
score_culture_loisir_brut - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | 0.00801 |
| std | 0.994 |
| min | -0.901 |
| 25% | -0.769 |
| 50% | -0.606 |
| 75% | 0.418 |
| max | 2.01 |
score_culture_loisir_ratio_1000 - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | -0.0118 |
| std | 0.963 |
| min | -0.439 |
| 25% | -0.351 |
| 50% | -0.285 |
| 75% | -0.0617 |
| max | 10.2 |
score_education_brut - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | 0.0223 |
| std | 1.01 |
| min | -0.88 |
| 25% | -0.806 |
| 50% | -0.675 |
| 75% | 1.03 |
| max | 1.51 |
score_education_ratio_1000 - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | -0.00618 |
| std | 0.999 |
| min | -2.36 |
| 25% | -0.717 |
| 50% | -0.173 |
| 75% | 0.348 |
| max | 3.79 |
score_s_curit__brut - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 1 |
| missing values | 0 |
score_s_curit__ratio_1000 - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 1 |
| missing values | 0 |
score_sant__brut - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 8 |
| missing values | 0 |
score_sant__ratio_1000 - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | 0.0219 |
| std | 0.989 |
| min | -2.16 |
| 25% | -0.327 |
| 50% | 0.0367 |
| 75% | 0.136 |
| max | 7.12 |
score_transport_brut - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | 0.0239 |
| std | 1.01 |
| min | -0.919 |
| 25% | -0.813 |
| 50% | -0.608 |
| 75% | 0.735 |
| max | 1.65 |
score_transport_ratio_1000 - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | -0.0144 |
| std | 0.982 |
| min | -2.76 |
| 25% | -0.875 |
| 50% | 0.21 |
| 75% | 0.839 |
| max | 3.1 |
source_imputation - Categorical
| Prediction dataset | |
|---|---|
| distinct values | 3 |
| missing values | 0 |
surface - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | -0.0223 |
| std | 0.993 |
| min | -2.08 |
| 25% | -0.606 |
| 50% | -0.148 |
| 75% | 0.408 |
| max | 9.2 |
Target analysis
prix_m2_vente - Numeric
| Prediction dataset | |
|---|---|
| count | 2,759 |
| mean | 2,550 |
| std | 1,070 |
| min | 216 |
| 25% | 1,710 |
| 50% | 2,440 |
| 75% | 3,300 |
| max | 7,440 |
Multivariate analysis
Model explainability
Note : the explainability graphs were generated using the test set only.
Global feature importance plot
Features contribution plots
- CODE_IRIS
- Revenu_fiscal_de_r__f__rence_par_habitant
- STATUT_COM_UU_Banlieue
- STATUT_COM_UU_Campagne
- STATUT_COM_UU_Ville isolée
- STATUT_COM_UU_Ville-centre
- TYP_IRIS_y
- UU2020
- anciennete_annonce
- annee
- annee_construction
- annonce_exclusive
- ascenseur
- bain
- balcon
- categorie_annonceur
- cave
- charges_copro
- chauffage_energie
- chauffage_mode
- chauffage_systeme
- classe_annee
- dpeC
- dpeL
- eau
- etage
- exposition_autre
- exposition_est
- exposition_nord
- exposition_sud
- ges_class
- ges_class_encoded
- logement_neuf
- mapCoordonneesLatitude
- mapCoordonneesLongitude
- nb_etages
- nb_logements_copro
- nb_pieces
- nb_toilettes
- places_parking
- score__conomie_brut
- score__conomie_ratio_1000
- score_commerce_brut
- score_commerce_ratio_1000
- score_culture_loisir_brut
- score_culture_loisir_ratio_1000
- score_education_brut
- score_education_ratio_1000
- score_s_curit__brut
- score_s_curit__ratio_1000
- score_sant__brut
- score_sant__ratio_1000
- score_transport_brut
- score_transport_ratio_1000
- source_imputation
- surface
CODE_IRIS -
Revenu_fiscal_de_r__f__rence_par_habitant -
STATUT_COM_UU_Banlieue -
STATUT_COM_UU_Campagne -
STATUT_COM_UU_Ville isolée -
STATUT_COM_UU_Ville-centre -
TYP_IRIS_y -
UU2020 -
anciennete_annonce -
annee -
annee_construction -
annonce_exclusive -
ascenseur -
bain -
balcon -
categorie_annonceur -
cave -
charges_copro -
chauffage_energie -
chauffage_mode -
chauffage_systeme -
classe_annee -
dpeC -
dpeL -
eau -
etage -
exposition_autre -
exposition_est -
exposition_nord -
exposition_sud -
ges_class -
ges_class_encoded -
logement_neuf -
mapCoordonneesLatitude -
mapCoordonneesLongitude -
nb_etages -
nb_logements_copro -
nb_pieces -
nb_toilettes -
places_parking -
score__conomie_brut -
score__conomie_ratio_1000 -
score_commerce_brut -
score_commerce_ratio_1000 -
score_culture_loisir_brut -
score_culture_loisir_ratio_1000 -
score_education_brut -
score_education_ratio_1000 -
score_s_curit__brut -
score_s_curit__ratio_1000 -
score_sant__brut -
score_sant__ratio_1000 -
score_transport_brut -
score_transport_ratio_1000 -
source_imputation -
surface -
Model performance
Univariate analysis of target variable
prix_m2_vente - Numeric
| True values | Prediction values | |
|---|---|---|
| count | 2,759 | 2,759 |
| mean | 2,550 | 2,560 |
| std | 1,070 | 930 |
| min | 216 | 508 |
| 25% | 1,710 | 1,820 |
| 50% | 2,440 | 2,440 |
| 75% | 3,300 | 3,230 |
| max | 7,440 | 6,880 |
Metrics
MAE : 355
R2 : 0.783
MSE : 250,000
MAPE : 0.171
MdAE : 251
Explained Variance : 0.783